Papers with domain-aware augmentation
Few-Shot (Dis)Agreement Identification in Online Discussions with Regularized and Augmented Meta-Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing annotated datasets do not cover all topics of interest. |
| Approach: | They propose a metric-based meta-learning approach that trains a meta-learner with two key abilities: decoding and generalizing domains. |
| Outcome: | The proposed approach can be quickly applied to analyze opinions for new topics with few labeled instances. |